slab.c 94.3 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
/*
 * linux/mm/slab.c
 * Written by Mark Hemment, 1996/97.
 * (markhe@nextd.demon.co.uk)
 *
 * kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli
 *
 * Major cleanup, different bufctl logic, per-cpu arrays
 *	(c) 2000 Manfred Spraul
 *
 * Cleanup, make the head arrays unconditional, preparation for NUMA
 * 	(c) 2002 Manfred Spraul
 *
 * An implementation of the Slab Allocator as described in outline in;
 *	UNIX Internals: The New Frontiers by Uresh Vahalia
 *	Pub: Prentice Hall	ISBN 0-13-101908-2
 * or with a little more detail in;
 *	The Slab Allocator: An Object-Caching Kernel Memory Allocator
 *	Jeff Bonwick (Sun Microsystems).
 *	Presented at: USENIX Summer 1994 Technical Conference
 *
 * The memory is organized in caches, one cache for each object type.
 * (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct)
 * Each cache consists out of many slabs (they are small (usually one
 * page long) and always contiguous), and each slab contains multiple
 * initialized objects.
 *
 * This means, that your constructor is used only for newly allocated
 * slabs and you must pass objects with the same intializations to
 * kmem_cache_free.
 *
 * Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM,
 * normal). If you need a special memory type, then must create a new
 * cache for that memory type.
 *
 * In order to reduce fragmentation, the slabs are sorted in 3 groups:
 *   full slabs with 0 free objects
 *   partial slabs
 *   empty slabs with no allocated objects
 *
 * If partial slabs exist, then new allocations come from these slabs,
 * otherwise from empty slabs or new slabs are allocated.
 *
 * kmem_cache_destroy() CAN CRASH if you try to allocate from the cache
 * during kmem_cache_destroy(). The caller must prevent concurrent allocs.
 *
 * Each cache has a short per-cpu head array, most allocs
 * and frees go into that array, and if that array overflows, then 1/2
 * of the entries in the array are given back into the global cache.
 * The head array is strictly LIFO and should improve the cache hit rates.
 * On SMP, it additionally reduces the spinlock operations.
 *
 * The c_cpuarray may not be read with enabled local interrupts - 
 * it's changed with a smp_call_function().
 *
 * SMP synchronization:
 *  constructors and destructors are called without any locking.
 *  Several members in kmem_cache_t and struct slab never change, they
 *	are accessed without any locking.
 *  The per-cpu arrays are never accessed from the wrong cpu, no locking,
 *  	and local interrupts are disabled so slab code is preempt-safe.
 *  The non-constant members are protected with a per-cache irq spinlock.
 *
 * Many thanks to Mark Hemment, who wrote another per-cpu slab patch
 * in 2000 - many ideas in the current implementation are derived from
 * his patch.
 *
 * Further notes from the original documentation:
 *
 * 11 April '97.  Started multi-threading - markhe
 *	The global cache-chain is protected by the semaphore 'cache_chain_sem'.
 *	The sem is only needed when accessing/extending the cache-chain, which
 *	can never happen inside an interrupt (kmem_cache_create(),
 *	kmem_cache_shrink() and kmem_cache_reap()).
 *
 *	At present, each engine can be growing a cache.  This should be blocked.
 *
78
79
80
81
82
83
84
85
86
 * 15 March 2005. NUMA slab allocator.
 *	Shai Fultheim <shai@scalex86.org>.
 *	Shobhit Dayal <shobhit@calsoftinc.com>
 *	Alok N Kataria <alokk@calsoftinc.com>
 *	Christoph Lameter <christoph@lameter.com>
 *
 *	Modified the slab allocator to be node aware on NUMA systems.
 *	Each node has its own list of partial, free and full slabs.
 *	All object allocations for a node occur from node specific slab lists.
Linus Torvalds's avatar
Linus Torvalds committed
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
 */

#include	<linux/config.h>
#include	<linux/slab.h>
#include	<linux/mm.h>
#include	<linux/swap.h>
#include	<linux/cache.h>
#include	<linux/interrupt.h>
#include	<linux/init.h>
#include	<linux/compiler.h>
#include	<linux/seq_file.h>
#include	<linux/notifier.h>
#include	<linux/kallsyms.h>
#include	<linux/cpu.h>
#include	<linux/sysctl.h>
#include	<linux/module.h>
#include	<linux/rcupdate.h>
104
#include	<linux/string.h>
105
#include	<linux/nodemask.h>
Linus Torvalds's avatar
Linus Torvalds committed
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201

#include	<asm/uaccess.h>
#include	<asm/cacheflush.h>
#include	<asm/tlbflush.h>
#include	<asm/page.h>

/*
 * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_DEBUG_INITIAL,
 *		  SLAB_RED_ZONE & SLAB_POISON.
 *		  0 for faster, smaller code (especially in the critical paths).
 *
 * STATS	- 1 to collect stats for /proc/slabinfo.
 *		  0 for faster, smaller code (especially in the critical paths).
 *
 * FORCED_DEBUG	- 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible)
 */

#ifdef CONFIG_DEBUG_SLAB
#define	DEBUG		1
#define	STATS		1
#define	FORCED_DEBUG	1
#else
#define	DEBUG		0
#define	STATS		0
#define	FORCED_DEBUG	0
#endif


/* Shouldn't this be in a header file somewhere? */
#define	BYTES_PER_WORD		sizeof(void *)

#ifndef cache_line_size
#define cache_line_size()	L1_CACHE_BYTES
#endif

#ifndef ARCH_KMALLOC_MINALIGN
/*
 * Enforce a minimum alignment for the kmalloc caches.
 * Usually, the kmalloc caches are cache_line_size() aligned, except when
 * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned.
 * Some archs want to perform DMA into kmalloc caches and need a guaranteed
 * alignment larger than BYTES_PER_WORD. ARCH_KMALLOC_MINALIGN allows that.
 * Note that this flag disables some debug features.
 */
#define ARCH_KMALLOC_MINALIGN 0
#endif

#ifndef ARCH_SLAB_MINALIGN
/*
 * Enforce a minimum alignment for all caches.
 * Intended for archs that get misalignment faults even for BYTES_PER_WORD
 * aligned buffers. Includes ARCH_KMALLOC_MINALIGN.
 * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables
 * some debug features.
 */
#define ARCH_SLAB_MINALIGN 0
#endif

#ifndef ARCH_KMALLOC_FLAGS
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif

/* Legal flag mask for kmem_cache_create(). */
#if DEBUG
# define CREATE_MASK	(SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \
			 SLAB_POISON | SLAB_HWCACHE_ALIGN | \
			 SLAB_NO_REAP | SLAB_CACHE_DMA | \
			 SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \
			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
			 SLAB_DESTROY_BY_RCU)
#else
# define CREATE_MASK	(SLAB_HWCACHE_ALIGN | SLAB_NO_REAP | \
			 SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \
			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
			 SLAB_DESTROY_BY_RCU)
#endif

/*
 * kmem_bufctl_t:
 *
 * Bufctl's are used for linking objs within a slab
 * linked offsets.
 *
 * This implementation relies on "struct page" for locating the cache &
 * slab an object belongs to.
 * This allows the bufctl structure to be small (one int), but limits
 * the number of objects a slab (not a cache) can contain when off-slab
 * bufctls are used. The limit is the size of the largest general cache
 * that does not use off-slab slabs.
 * For 32bit archs with 4 kB pages, is this 56.
 * This is not serious, as it is only for large objects, when it is unwise
 * to have too many per slab.
 * Note: This limit can be raised by introducing a general cache whose size
 * is less than 512 (PAGE_SIZE<<3), but greater than 256.
 */

202
typedef unsigned int kmem_bufctl_t;
Linus Torvalds's avatar
Linus Torvalds committed
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
#define BUFCTL_END	(((kmem_bufctl_t)(~0U))-0)
#define BUFCTL_FREE	(((kmem_bufctl_t)(~0U))-1)
#define	SLAB_LIMIT	(((kmem_bufctl_t)(~0U))-2)

/* Max number of objs-per-slab for caches which use off-slab slabs.
 * Needed to avoid a possible looping condition in cache_grow().
 */
static unsigned long offslab_limit;

/*
 * struct slab
 *
 * Manages the objs in a slab. Placed either at the beginning of mem allocated
 * for a slab, or allocated from an general cache.
 * Slabs are chained into three list: fully used, partial, fully free slabs.
 */
struct slab {
	struct list_head	list;
	unsigned long		colouroff;
	void			*s_mem;		/* including colour offset */
	unsigned int		inuse;		/* num of objs active in slab */
	kmem_bufctl_t		free;
225
	unsigned short          nodeid;
Linus Torvalds's avatar
Linus Torvalds committed
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
};

/*
 * struct slab_rcu
 *
 * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
 * arrange for kmem_freepages to be called via RCU.  This is useful if
 * we need to approach a kernel structure obliquely, from its address
 * obtained without the usual locking.  We can lock the structure to
 * stabilize it and check it's still at the given address, only if we
 * can be sure that the memory has not been meanwhile reused for some
 * other kind of object (which our subsystem's lock might corrupt).
 *
 * rcu_read_lock before reading the address, then rcu_read_unlock after
 * taking the spinlock within the structure expected at that address.
 *
 * We assume struct slab_rcu can overlay struct slab when destroying.
 */
struct slab_rcu {
	struct rcu_head		head;
	kmem_cache_t		*cachep;
	void			*addr;
};

/*
 * struct array_cache
 *
 * Purpose:
 * - LIFO ordering, to hand out cache-warm objects from _alloc
 * - reduce the number of linked list operations
 * - reduce spinlock operations
 *
 * The limit is stored in the per-cpu structure to reduce the data cache
 * footprint.
 *
 */
struct array_cache {
	unsigned int avail;
	unsigned int limit;
	unsigned int batchcount;
	unsigned int touched;
267
268
269
270
271
272
273
	spinlock_t lock;
	void *entry[0];		/*
				 * Must have this definition in here for the proper
				 * alignment of array_cache. Also simplifies accessing
				 * the entries.
				 * [0] is for gcc 2.95. It should really be [].
				 */
Linus Torvalds's avatar
Linus Torvalds committed
274
275
276
277
278
279
280
281
282
283
284
285
};

/* bootstrap: The caches do not work without cpuarrays anymore,
 * but the cpuarrays are allocated from the generic caches...
 */
#define BOOT_CPUCACHE_ENTRIES	1
struct arraycache_init {
	struct array_cache cache;
	void * entries[BOOT_CPUCACHE_ENTRIES];
};

/*
286
 * The slab lists for all objects.
Linus Torvalds's avatar
Linus Torvalds committed
287
288
289
290
291
292
293
 */
struct kmem_list3 {
	struct list_head	slabs_partial;	/* partial list first, better asm code */
	struct list_head	slabs_full;
	struct list_head	slabs_free;
	unsigned long	free_objects;
	unsigned long	next_reap;
294
295
296
297
298
	int		free_touched;
	unsigned int 	free_limit;
	spinlock_t      list_lock;
	struct array_cache	*shared;	/* shared per node */
	struct array_cache	**alien;	/* on other nodes */
Linus Torvalds's avatar
Linus Torvalds committed
299
300
};

301
302
303
304
305
306
307
308
309
310
/*
 * Need this for bootstrapping a per node allocator.
 */
#define NUM_INIT_LISTS (2 * MAX_NUMNODES + 1)
struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
#define	CACHE_CACHE 0
#define	SIZE_AC 1
#define	SIZE_L3 (1 + MAX_NUMNODES)

/*
311
 * This function must be completely optimized away if
312
313
314
315
 * a constant is passed to it. Mostly the same as
 * what is in linux/slab.h except it returns an
 * index.
 */
316
static __always_inline int index_of(const size_t size)
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
{
	if (__builtin_constant_p(size)) {
		int i = 0;

#define CACHE(x) \
	if (size <=x) \
		return i; \
	else \
		i++;
#include "linux/kmalloc_sizes.h"
#undef CACHE
		{
			extern void __bad_size(void);
			__bad_size();
		}
332
333
	} else
		BUG();
334
335
336
337
338
	return 0;
}

#define INDEX_AC index_of(sizeof(struct arraycache_init))
#define INDEX_L3 index_of(sizeof(struct kmem_list3))
Linus Torvalds's avatar
Linus Torvalds committed
339

340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
static inline void kmem_list3_init(struct kmem_list3 *parent)
{
	INIT_LIST_HEAD(&parent->slabs_full);
	INIT_LIST_HEAD(&parent->slabs_partial);
	INIT_LIST_HEAD(&parent->slabs_free);
	parent->shared = NULL;
	parent->alien = NULL;
	spin_lock_init(&parent->list_lock);
	parent->free_objects = 0;
	parent->free_touched = 0;
}

#define MAKE_LIST(cachep, listp, slab, nodeid)	\
	do {	\
		INIT_LIST_HEAD(listp);		\
		list_splice(&(cachep->nodelists[nodeid]->slab), listp); \
	} while (0)

#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)			\
	do {					\
	MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid);	\
	MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
	} while (0)
Linus Torvalds's avatar
Linus Torvalds committed
364
365
366
367
368
369
370
371
372
373
374
375

/*
 * kmem_cache_t
 *
 * manages a cache.
 */
	
struct kmem_cache_s {
/* 1) per-cpu data, touched during every alloc/free */
	struct array_cache	*array[NR_CPUS];
	unsigned int		batchcount;
	unsigned int		limit;
376
	unsigned int 		shared;
Linus Torvalds's avatar
Linus Torvalds committed
377
	unsigned int		objsize;
378
379
/* 2) touched by every alloc & free from the backend */
	struct kmem_list3	*nodelists[MAX_NUMNODES];
Linus Torvalds's avatar
Linus Torvalds committed
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
	unsigned int	 	flags;	/* constant flags */
	unsigned int		num;	/* # of objs per slab */
	spinlock_t		spinlock;

/* 3) cache_grow/shrink */
	/* order of pgs per slab (2^n) */
	unsigned int		gfporder;

	/* force GFP flags, e.g. GFP_DMA */
	unsigned int		gfpflags;

	size_t			colour;		/* cache colouring range */
	unsigned int		colour_off;	/* colour offset */
	unsigned int		colour_next;	/* cache colouring */
	kmem_cache_t		*slabp_cache;
	unsigned int		slab_size;
	unsigned int		dflags;		/* dynamic flags */

	/* constructor func */
	void (*ctor)(void *, kmem_cache_t *, unsigned long);

	/* de-constructor func */
	void (*dtor)(void *, kmem_cache_t *, unsigned long);

/* 4) cache creation/removal */
	const char		*name;
	struct list_head	next;

/* 5) statistics */
#if STATS
	unsigned long		num_active;
	unsigned long		num_allocations;
	unsigned long		high_mark;
	unsigned long		grown;
	unsigned long		reaped;
	unsigned long 		errors;
	unsigned long		max_freeable;
	unsigned long		node_allocs;
418
	unsigned long		node_frees;
Linus Torvalds's avatar
Linus Torvalds committed
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
	atomic_t		allochit;
	atomic_t		allocmiss;
	atomic_t		freehit;
	atomic_t		freemiss;
#endif
#if DEBUG
	int			dbghead;
	int			reallen;
#endif
};

#define CFLGS_OFF_SLAB		(0x80000000UL)
#define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)

#define BATCHREFILL_LIMIT	16
/* Optimization question: fewer reaps means less 
 * probability for unnessary cpucache drain/refill cycles.
 *
 * OTHO the cpuarrays can contain lots of objects,
 * which could lock up otherwise freeable slabs.
 */
#define REAPTIMEOUT_CPUC	(2*HZ)
#define REAPTIMEOUT_LIST3	(4*HZ)

#if STATS
#define	STATS_INC_ACTIVE(x)	((x)->num_active++)
#define	STATS_DEC_ACTIVE(x)	((x)->num_active--)
#define	STATS_INC_ALLOCED(x)	((x)->num_allocations++)
#define	STATS_INC_GROWN(x)	((x)->grown++)
#define	STATS_INC_REAPED(x)	((x)->reaped++)
#define	STATS_SET_HIGH(x)	do { if ((x)->num_active > (x)->high_mark) \
					(x)->high_mark = (x)->num_active; \
				} while (0)
#define	STATS_INC_ERR(x)	((x)->errors++)
#define	STATS_INC_NODEALLOCS(x)	((x)->node_allocs++)
454
#define	STATS_INC_NODEFREES(x)	((x)->node_frees++)
Linus Torvalds's avatar
Linus Torvalds committed
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
#define	STATS_SET_FREEABLE(x, i) \
				do { if ((x)->max_freeable < i) \
					(x)->max_freeable = i; \
				} while (0)

#define STATS_INC_ALLOCHIT(x)	atomic_inc(&(x)->allochit)
#define STATS_INC_ALLOCMISS(x)	atomic_inc(&(x)->allocmiss)
#define STATS_INC_FREEHIT(x)	atomic_inc(&(x)->freehit)
#define STATS_INC_FREEMISS(x)	atomic_inc(&(x)->freemiss)
#else
#define	STATS_INC_ACTIVE(x)	do { } while (0)
#define	STATS_DEC_ACTIVE(x)	do { } while (0)
#define	STATS_INC_ALLOCED(x)	do { } while (0)
#define	STATS_INC_GROWN(x)	do { } while (0)
#define	STATS_INC_REAPED(x)	do { } while (0)
#define	STATS_SET_HIGH(x)	do { } while (0)
#define	STATS_INC_ERR(x)	do { } while (0)
#define	STATS_INC_NODEALLOCS(x)	do { } while (0)
473
#define	STATS_INC_NODEFREES(x)	do { } while (0)
Linus Torvalds's avatar
Linus Torvalds committed
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
#define	STATS_SET_FREEABLE(x, i) \
				do { } while (0)

#define STATS_INC_ALLOCHIT(x)	do { } while (0)
#define STATS_INC_ALLOCMISS(x)	do { } while (0)
#define STATS_INC_FREEHIT(x)	do { } while (0)
#define STATS_INC_FREEMISS(x)	do { } while (0)
#endif

#if DEBUG
/* Magic nums for obj red zoning.
 * Placed in the first word before and the first word after an obj.
 */
#define	RED_INACTIVE	0x5A2CF071UL	/* when obj is inactive */
#define	RED_ACTIVE	0x170FC2A5UL	/* when obj is active */

/* ...and for poisoning */
#define	POISON_INUSE	0x5a	/* for use-uninitialised poisoning */
#define POISON_FREE	0x6b	/* for use-after-free poisoning */
#define	POISON_END	0xa5	/* end-byte of poisoning */

/* memory layout of objects:
 * 0		: objp
 * 0 .. cachep->dbghead - BYTES_PER_WORD - 1: padding. This ensures that
 * 		the end of an object is aligned with the end of the real
 * 		allocation. Catches writes behind the end of the allocation.
 * cachep->dbghead - BYTES_PER_WORD .. cachep->dbghead - 1:
 * 		redzone word.
 * cachep->dbghead: The real object.
 * cachep->objsize - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
 * cachep->objsize - 1* BYTES_PER_WORD: last caller address [BYTES_PER_WORD long]
 */
static int obj_dbghead(kmem_cache_t *cachep)
{
	return cachep->dbghead;
}

static int obj_reallen(kmem_cache_t *cachep)
{
	return cachep->reallen;
}

static unsigned long *dbg_redzone1(kmem_cache_t *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
	return (unsigned long*) (objp+obj_dbghead(cachep)-BYTES_PER_WORD);
}

static unsigned long *dbg_redzone2(kmem_cache_t *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
	if (cachep->flags & SLAB_STORE_USER)
		return (unsigned long*) (objp+cachep->objsize-2*BYTES_PER_WORD);
	return (unsigned long*) (objp+cachep->objsize-BYTES_PER_WORD);
}

static void **dbg_userword(kmem_cache_t *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_STORE_USER));
	return (void**)(objp+cachep->objsize-BYTES_PER_WORD);
}

#else

#define obj_dbghead(x)			0
#define obj_reallen(cachep)		(cachep->objsize)
#define dbg_redzone1(cachep, objp)	({BUG(); (unsigned long *)NULL;})
#define dbg_redzone2(cachep, objp)	({BUG(); (unsigned long *)NULL;})
#define dbg_userword(cachep, objp)	({BUG(); (void **)NULL;})

#endif

/*
 * Maximum size of an obj (in 2^order pages)
 * and absolute limit for the gfp order.
 */
#if defined(CONFIG_LARGE_ALLOCS)
#define	MAX_OBJ_ORDER	13	/* up to 32Mb */
#define	MAX_GFP_ORDER	13	/* up to 32Mb */
#elif defined(CONFIG_MMU)
#define	MAX_OBJ_ORDER	5	/* 32 pages */
#define	MAX_GFP_ORDER	5	/* 32 pages */
#else
#define	MAX_OBJ_ORDER	8	/* up to 1Mb */
#define	MAX_GFP_ORDER	8	/* up to 1Mb */
#endif

/*
 * Do not go above this order unless 0 objects fit into the slab.
 */
#define	BREAK_GFP_ORDER_HI	1
#define	BREAK_GFP_ORDER_LO	0
static int slab_break_gfp_order = BREAK_GFP_ORDER_LO;

/* Macros for storing/retrieving the cachep and or slab from the
 * global 'mem_map'. These are used to find the slab an obj belongs to.
 * With kfree(), these are used to find the cache which an obj belongs to.
 */
#define	SET_PAGE_CACHE(pg,x)  ((pg)->lru.next = (struct list_head *)(x))
#define	GET_PAGE_CACHE(pg)    ((kmem_cache_t *)(pg)->lru.next)
#define	SET_PAGE_SLAB(pg,x)   ((pg)->lru.prev = (struct list_head *)(x))
#define	GET_PAGE_SLAB(pg)     ((struct slab *)(pg)->lru.prev)

/* These are the default caches for kmalloc. Custom caches can have other sizes. */
struct cache_sizes malloc_sizes[] = {
#define CACHE(x) { .cs_size = (x) },
#include <linux/kmalloc_sizes.h>
	CACHE(ULONG_MAX)
#undef CACHE
};
EXPORT_SYMBOL(malloc_sizes);

/* Must match cache_sizes above. Out of line to keep cache footprint low. */
struct cache_names {
	char *name;
	char *name_dma;
};

static struct cache_names __initdata cache_names[] = {
#define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" },
#include <linux/kmalloc_sizes.h>
	{ NULL, }
#undef CACHE
};

static struct arraycache_init initarray_cache __initdata =
	{ { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
static struct arraycache_init initarray_generic =
	{ { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} };

/* internal cache of cache description objs */
static kmem_cache_t cache_cache = {
	.batchcount	= 1,
	.limit		= BOOT_CPUCACHE_ENTRIES,
608
	.shared		= 1,
Linus Torvalds's avatar
Linus Torvalds committed
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
	.objsize	= sizeof(kmem_cache_t),
	.flags		= SLAB_NO_REAP,
	.spinlock	= SPIN_LOCK_UNLOCKED,
	.name		= "kmem_cache",
#if DEBUG
	.reallen	= sizeof(kmem_cache_t),
#endif
};

/* Guard access to the cache-chain. */
static struct semaphore	cache_chain_sem;
static struct list_head cache_chain;

/*
 * vm_enough_memory() looks at this to determine how many
 * slab-allocated pages are possibly freeable under pressure
 *
 * SLAB_RECLAIM_ACCOUNT turns this on per-slab
 */
atomic_t slab_reclaim_pages;

/*
 * chicken and egg problem: delay the per-cpu array allocation
 * until the general caches are up.
 */
static enum {
	NONE,
636
637
	PARTIAL_AC,
	PARTIAL_L3,
Linus Torvalds's avatar
Linus Torvalds committed
638
639
640
641
642
	FULL
} g_cpucache_up;

static DEFINE_PER_CPU(struct work_struct, reap_work);

643
static void free_block(kmem_cache_t* cachep, void** objpp, int len, int node);
Linus Torvalds's avatar
Linus Torvalds committed
644
645
static void enable_cpucache (kmem_cache_t *cachep);
static void cache_reap (void *unused);
646
static int __node_shrink(kmem_cache_t *cachep, int node);
Linus Torvalds's avatar
Linus Torvalds committed
647
648
649
650
651
652

static inline struct array_cache *ac_data(kmem_cache_t *cachep)
{
	return cachep->array[smp_processor_id()];
}

653
654
static inline kmem_cache_t *__find_general_cachep(size_t size,
						unsigned int __nocast gfpflags)
Linus Torvalds's avatar
Linus Torvalds committed
655
656
657
658
659
660
661
662
{
	struct cache_sizes *csizep = malloc_sizes;

#if DEBUG
	/* This happens if someone tries to call
 	* kmem_cache_create(), or __kmalloc(), before
 	* the generic caches are initialized.
 	*/
663
	BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
Linus Torvalds's avatar
Linus Torvalds committed
664
665
666
667
668
#endif
	while (size > csizep->cs_size)
		csizep++;

	/*
669
	 * Really subtle: The last entry with cs->cs_size==ULONG_MAX
Linus Torvalds's avatar
Linus Torvalds committed
670
671
672
673
674
675
676
677
	 * has cs_{dma,}cachep==NULL. Thus no special case
	 * for large kmalloc calls required.
	 */
	if (unlikely(gfpflags & GFP_DMA))
		return csizep->cs_dmacachep;
	return csizep->cs_cachep;
}

678
679
kmem_cache_t *kmem_find_general_cachep(size_t size,
		unsigned int __nocast gfpflags)
680
681
682
683
684
{
	return __find_general_cachep(size, gfpflags);
}
EXPORT_SYMBOL(kmem_find_general_cachep);

Linus Torvalds's avatar
Linus Torvalds committed
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
/* Cal the num objs, wastage, and bytes left over for a given slab size. */
static void cache_estimate(unsigned long gfporder, size_t size, size_t align,
		 int flags, size_t *left_over, unsigned int *num)
{
	int i;
	size_t wastage = PAGE_SIZE<<gfporder;
	size_t extra = 0;
	size_t base = 0;

	if (!(flags & CFLGS_OFF_SLAB)) {
		base = sizeof(struct slab);
		extra = sizeof(kmem_bufctl_t);
	}
	i = 0;
	while (i*size + ALIGN(base+i*extra, align) <= wastage)
		i++;
	if (i > 0)
		i--;

	if (i > SLAB_LIMIT)
		i = SLAB_LIMIT;

	*num = i;
	wastage -= i*size;
	wastage -= ALIGN(base+i*extra, align);
	*left_over = wastage;
}

#define slab_error(cachep, msg) __slab_error(__FUNCTION__, cachep, msg)

static void __slab_error(const char *function, kmem_cache_t *cachep, char *msg)
{
	printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
		function, cachep->name, msg);
	dump_stack();
}

/*
 * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
 * via the workqueue/eventd.
 * Add the CPU number into the expiration time to minimize the possibility of
 * the CPUs getting into lockstep and contending for the global cache chain
 * lock.
 */
static void __devinit start_cpu_timer(int cpu)
{
	struct work_struct *reap_work = &per_cpu(reap_work, cpu);

	/*
	 * When this gets called from do_initcalls via cpucache_init(),
	 * init_workqueues() has already run, so keventd will be setup
	 * at that time.
	 */
	if (keventd_up() && reap_work->func == NULL) {
		INIT_WORK(reap_work, cache_reap, NULL);
		schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
	}
}

744
static struct array_cache *alloc_arraycache(int node, int entries,
Linus Torvalds's avatar
Linus Torvalds committed
745
746
747
748
749
						int batchcount)
{
	int memsize = sizeof(void*)*entries+sizeof(struct array_cache);
	struct array_cache *nc = NULL;

750
	nc = kmalloc_node(memsize, GFP_KERNEL, node);
Linus Torvalds's avatar
Linus Torvalds committed
751
752
753
754
755
	if (nc) {
		nc->avail = 0;
		nc->limit = entries;
		nc->batchcount = batchcount;
		nc->touched = 0;
756
		spin_lock_init(&nc->lock);
Linus Torvalds's avatar
Linus Torvalds committed
757
758
759
760
	}
	return nc;
}

761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
#ifdef CONFIG_NUMA
static inline struct array_cache **alloc_alien_cache(int node, int limit)
{
	struct array_cache **ac_ptr;
	int memsize = sizeof(void*)*MAX_NUMNODES;
	int i;

	if (limit > 1)
		limit = 12;
	ac_ptr = kmalloc_node(memsize, GFP_KERNEL, node);
	if (ac_ptr) {
		for_each_node(i) {
			if (i == node || !node_online(i)) {
				ac_ptr[i] = NULL;
				continue;
			}
			ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d);
			if (!ac_ptr[i]) {
				for (i--; i <=0; i--)
					kfree(ac_ptr[i]);
				kfree(ac_ptr);
				return NULL;
			}
		}
	}
	return ac_ptr;
}

static inline void free_alien_cache(struct array_cache **ac_ptr)
{
	int i;

	if (!ac_ptr)
		return;

	for_each_node(i)
		kfree(ac_ptr[i]);

	kfree(ac_ptr);
}

static inline void __drain_alien_cache(kmem_cache_t *cachep, struct array_cache *ac, int node)
{
	struct kmem_list3 *rl3 = cachep->nodelists[node];

	if (ac->avail) {
		spin_lock(&rl3->list_lock);
808
		free_block(cachep, ac->entry, ac->avail, node);
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
		ac->avail = 0;
		spin_unlock(&rl3->list_lock);
	}
}

static void drain_alien_cache(kmem_cache_t *cachep, struct kmem_list3 *l3)
{
	int i=0;
	struct array_cache *ac;
	unsigned long flags;

	for_each_online_node(i) {
		ac = l3->alien[i];
		if (ac) {
			spin_lock_irqsave(&ac->lock, flags);
			__drain_alien_cache(cachep, ac, i);
			spin_unlock_irqrestore(&ac->lock, flags);
		}
	}
}
#else
#define alloc_alien_cache(node, limit) do { } while (0)
#define free_alien_cache(ac_ptr) do { } while (0)
#define drain_alien_cache(cachep, l3) do { } while (0)
#endif

Linus Torvalds's avatar
Linus Torvalds committed
835
836
837
838
839
static int __devinit cpuup_callback(struct notifier_block *nfb,
				  unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	kmem_cache_t* cachep;
840
841
842
843
	struct kmem_list3 *l3 = NULL;
	int node = cpu_to_node(cpu);
	int memsize = sizeof(struct kmem_list3);
	struct array_cache *nc = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
844
845
846
847

	switch (action) {
	case CPU_UP_PREPARE:
		down(&cache_chain_sem);
848
849
850
851
852
853
		/* we need to do this right in the beginning since
		 * alloc_arraycache's are going to use this list.
		 * kmalloc_node allows us to add the slab to the right
		 * kmem_list3 and not this cpu's kmem_list3
		 */

Linus Torvalds's avatar
Linus Torvalds committed
854
		list_for_each_entry(cachep, &cache_chain, next) {
855
856
857
858
859
860
861
862
863
864
865
866
867
868
			/* setup the size64 kmemlist for cpu before we can
			 * begin anything. Make sure some other cpu on this
			 * node has not already allocated this
			 */
			if (!cachep->nodelists[node]) {
				if (!(l3 = kmalloc_node(memsize,
						GFP_KERNEL, node)))
					goto bad;
				kmem_list3_init(l3);
				l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
				  ((unsigned long)cachep)%REAPTIMEOUT_LIST3;

				cachep->nodelists[node] = l3;
			}
Linus Torvalds's avatar
Linus Torvalds committed
869

870
871
872
873
874
875
876
877
878
879
880
881
			spin_lock_irq(&cachep->nodelists[node]->list_lock);
			cachep->nodelists[node]->free_limit =
				(1 + nr_cpus_node(node)) *
				cachep->batchcount + cachep->num;
			spin_unlock_irq(&cachep->nodelists[node]->list_lock);
		}

		/* Now we can go ahead with allocating the shared array's
		  & array cache's */
		list_for_each_entry(cachep, &cache_chain, next) {
			nc = alloc_arraycache(node, cachep->limit,
					cachep->batchcount);
Linus Torvalds's avatar
Linus Torvalds committed
882
883
884
885
			if (!nc)
				goto bad;
			cachep->array[cpu] = nc;

886
887
888
889
890
891
892
893
894
895
896
897
			l3 = cachep->nodelists[node];
			BUG_ON(!l3);
			if (!l3->shared) {
				if (!(nc = alloc_arraycache(node,
					cachep->shared*cachep->batchcount,
					0xbaadf00d)))
					goto  bad;

				/* we are serialised from CPU_DEAD or
				  CPU_UP_CANCELLED by the cpucontrol lock */
				l3->shared = nc;
			}
Linus Torvalds's avatar
Linus Torvalds committed
898
899
900
901
902
903
904
905
906
907
908
909
910
911
		}
		up(&cache_chain_sem);
		break;
	case CPU_ONLINE:
		start_cpu_timer(cpu);
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
		/* fall thru */
	case CPU_UP_CANCELED:
		down(&cache_chain_sem);

		list_for_each_entry(cachep, &cache_chain, next) {
			struct array_cache *nc;
912
			cpumask_t mask;
Linus Torvalds's avatar
Linus Torvalds committed
913

914
			mask = node_to_cpumask(node);
Linus Torvalds's avatar
Linus Torvalds committed
915
916
917
918
			spin_lock_irq(&cachep->spinlock);
			/* cpu is dead; no one can alloc from it. */
			nc = cachep->array[cpu];
			cachep->array[cpu] = NULL;
919
920
921
922
923
924
925
926
927
928
			l3 = cachep->nodelists[node];

			if (!l3)
				goto unlock_cache;

			spin_lock(&l3->list_lock);

			/* Free limit for this kmem_list3 */
			l3->free_limit -= cachep->batchcount;
			if (nc)
929
				free_block(cachep, nc->entry, nc->avail, node);
930
931
932
933
934
935
936
937

			if (!cpus_empty(mask)) {
                                spin_unlock(&l3->list_lock);
                                goto unlock_cache;
                        }

			if (l3->shared) {
				free_block(cachep, l3->shared->entry,
938
						l3->shared->avail, node);
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
				kfree(l3->shared);
				l3->shared = NULL;
			}
			if (l3->alien) {
				drain_alien_cache(cachep, l3);
				free_alien_cache(l3->alien);
				l3->alien = NULL;
			}

			/* free slabs belonging to this node */
			if (__node_shrink(cachep, node)) {
				cachep->nodelists[node] = NULL;
				spin_unlock(&l3->list_lock);
				kfree(l3);
			} else {
				spin_unlock(&l3->list_lock);
			}
unlock_cache:
Linus Torvalds's avatar
Linus Torvalds committed
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
			spin_unlock_irq(&cachep->spinlock);
			kfree(nc);
		}
		up(&cache_chain_sem);
		break;
#endif
	}
	return NOTIFY_OK;
bad:
	up(&cache_chain_sem);
	return NOTIFY_BAD;
}

static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 };

972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
/*
 * swap the static kmem_list3 with kmalloced memory
 */
static void init_list(kmem_cache_t *cachep, struct kmem_list3 *list,
		int nodeid)
{
	struct kmem_list3 *ptr;

	BUG_ON(cachep->nodelists[nodeid] != list);
	ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid);
	BUG_ON(!ptr);

	local_irq_disable();
	memcpy(ptr, list, sizeof(struct kmem_list3));
	MAKE_ALL_LISTS(cachep, ptr, nodeid);
	cachep->nodelists[nodeid] = ptr;
	local_irq_enable();
}

Linus Torvalds's avatar
Linus Torvalds committed
991
992
993
994
995
996
997
998
/* Initialisation.
 * Called after the gfp() functions have been enabled, and before smp_init().
 */
void __init kmem_cache_init(void)
{
	size_t left_over;
	struct cache_sizes *sizes;
	struct cache_names *names;
999
1000
1001
1002
1003
1004
1005
	int i;

	for (i = 0; i < NUM_INIT_LISTS; i++) {
		kmem_list3_init(&initkmem_list3[i]);
		if (i < MAX_NUMNODES)
			cache_cache.nodelists[i] = NULL;
	}
Linus Torvalds's avatar
Linus Torvalds committed
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018

	/*
	 * Fragmentation resistance on low memory - only use bigger
	 * page orders on machines with more than 32MB of memory.
	 */
	if (num_physpages > (32 << 20) >> PAGE_SHIFT)
		slab_break_gfp_order = BREAK_GFP_ORDER_HI;

	/* Bootstrap is tricky, because several objects are allocated
	 * from caches that do not exist yet:
	 * 1) initialize the cache_cache cache: it contains the kmem_cache_t
	 *    structures of all caches, except cache_cache itself: cache_cache
	 *    is statically allocated.
1019
1020
1021
	 *    Initially an __init data area is used for the head array and the
	 *    kmem_list3 structures, it's replaced with a kmalloc allocated
	 *    array at the end of the bootstrap.
Linus Torvalds's avatar
Linus Torvalds committed
1022
	 * 2) Create the first kmalloc cache.
1023
1024
1025
1026
	 *    The kmem_cache_t for the new cache is allocated normally.
	 *    An __init data area is used for the head array.
	 * 3) Create the remaining kmalloc caches, with minimally sized
	 *    head arrays.
Linus Torvalds's avatar
Linus Torvalds committed
1027
1028
	 * 4) Replace the __init data head arrays for cache_cache and the first
	 *    kmalloc cache with kmalloc allocated arrays.
1029
1030
1031
	 * 5) Replace the __init data for kmem_list3 for cache_cache and
	 *    the other cache's with kmalloc allocated memory.
	 * 6) Resize the head arrays of the kmalloc caches to their final sizes.
Linus Torvalds's avatar
Linus Torvalds committed
1032
1033
1034
1035
1036
1037
1038
1039
	 */

	/* 1) create the cache_cache */
	init_MUTEX(&cache_chain_sem);
	INIT_LIST_HEAD(&cache_chain);
	list_add(&cache_cache.next, &cache_chain);
	cache_cache.colour_off = cache_line_size();
	cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
1040
	cache_cache.nodelists[numa_node_id()] = &initkmem_list3[CACHE_CACHE];
Linus Torvalds's avatar
Linus Torvalds committed
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057

	cache_cache.objsize = ALIGN(cache_cache.objsize, cache_line_size());

	cache_estimate(0, cache_cache.objsize, cache_line_size(), 0,
				&left_over, &cache_cache.num);
	if (!cache_cache.num)
		BUG();

	cache_cache.colour = left_over/cache_cache.colour_off;
	cache_cache.colour_next = 0;
	cache_cache.slab_size = ALIGN(cache_cache.num*sizeof(kmem_bufctl_t) +
				sizeof(struct slab), cache_line_size());

	/* 2+3) create the kmalloc caches */
	sizes = malloc_sizes;
	names = cache_names;

1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
	/* Initialize the caches that provide memory for the array cache
	 * and the kmem_list3 structures first.
	 * Without this, further allocations will bug
	 */

	sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name,
				sizes[INDEX_AC].cs_size, ARCH_KMALLOC_MINALIGN,
				(ARCH_KMALLOC_FLAGS | SLAB_PANIC), NULL, NULL);

	if (INDEX_AC != INDEX_L3)
		sizes[INDEX_L3].cs_cachep =
			kmem_cache_create(names[INDEX_L3].name,
				sizes[INDEX_L3].cs_size, ARCH_KMALLOC_MINALIGN,
				(ARCH_KMALLOC_FLAGS | SLAB_PANIC), NULL, NULL);

Linus Torvalds's avatar
Linus Torvalds committed
1073
	while (sizes->cs_size != ULONG_MAX) {
1074
1075
		/*
		 * For performance, all the general caches are L1 aligned.
Linus Torvalds's avatar
Linus Torvalds committed
1076
1077
1078
		 * This should be particularly beneficial on SMP boxes, as it
		 * eliminates "false sharing".
		 * Note for systems short on memory removing the alignment will
1079
1080
1081
1082
1083
1084
		 * allow tighter packing of the smaller caches.
		 */
		if(!sizes->cs_cachep)
			sizes->cs_cachep = kmem_cache_create(names->name,
				sizes->cs_size, ARCH_KMALLOC_MINALIGN,
				(ARCH_KMALLOC_FLAGS | SLAB_PANIC), NULL, NULL);
Linus Torvalds's avatar
Linus Torvalds committed
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102

		/* Inc off-slab bufctl limit until the ceiling is hit. */
		if (!(OFF_SLAB(sizes->cs_cachep))) {
			offslab_limit = sizes->cs_size-sizeof(struct slab);
			offslab_limit /= sizeof(kmem_bufctl_t);
		}

		sizes->cs_dmacachep = kmem_cache_create(names->name_dma,
			sizes->cs_size, ARCH_KMALLOC_MINALIGN,
			(ARCH_KMALLOC_FLAGS | SLAB_CACHE_DMA | SLAB_PANIC),
			NULL, NULL);

		sizes++;
		names++;
	}
	/* 4) Replace the bootstrap head arrays */
	{
		void * ptr;
1103

Linus Torvalds's avatar
Linus Torvalds committed
1104
		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
1105

Linus Torvalds's avatar
Linus Torvalds committed
1106
1107
		local_irq_disable();
		BUG_ON(ac_data(&cache_cache) != &initarray_cache.cache);
1108
1109
		memcpy(ptr, ac_data(&cache_cache),
				sizeof(struct arraycache_init));
Linus Torvalds's avatar
Linus Torvalds committed
1110
1111
		cache_cache.array[smp_processor_id()] = ptr;
		local_irq_enable();
1112

Linus Torvalds's avatar
Linus Torvalds committed
1113
		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
1114

Linus Torvalds's avatar
Linus Torvalds committed
1115
		local_irq_disable();
1116
1117
1118
		BUG_ON(ac_data(malloc_sizes[INDEX_AC].cs_cachep)
				!= &initarray_generic.cache);
		memcpy(ptr, ac_data(malloc_sizes[INDEX_AC].cs_cachep),
Linus Torvalds's avatar
Linus Torvalds committed
1119
				sizeof(struct arraycache_init));
1120
1121
		malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
						ptr;
Linus Torvalds's avatar
Linus Torvalds committed
1122
1123
		local_irq_enable();
	}
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
	/* 5) Replace the bootstrap kmem_list3's */
	{
		int node;
		/* Replace the static kmem_list3 structures for the boot cpu */
		init_list(&cache_cache, &initkmem_list3[CACHE_CACHE],
				numa_node_id());

		for_each_online_node(node) {
			init_list(malloc_sizes[INDEX_AC].cs_cachep,
					&initkmem_list3[SIZE_AC+node], node);

			if (INDEX_AC != INDEX_L3) {
				init_list(malloc_sizes[INDEX_L3].cs_cachep,
						&initkmem_list3[SIZE_L3+node],
						node);
			}
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
1142

1143
	/* 6) resize the head arrays to their final sizes */
Linus Torvalds's avatar
Linus Torvalds committed
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
	{
		kmem_cache_t *cachep;
		down(&cache_chain_sem);
		list_for_each_entry(cachep, &cache_chain, next)
			enable_cpucache(cachep);
		up(&cache_chain_sem);
	}

	/* Done! */
	g_cpucache_up = FULL;

	/* Register a cpu startup notifier callback
	 * that initializes ac_data for all new cpus
	 */
	register_cpu_notifier(&cpucache_notifier);

	/* The reap timers are started later, with a module init call:
	 * That part of the kernel is not yet operational.
	 */
}

static int __init cpucache_init(void)
{
	int cpu;

	/* 
	 * Register the timers that return unneeded
	 * pages to gfp.
	 */
1173
1174
	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);
Linus Torvalds's avatar
Linus Torvalds committed
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452

	return 0;
}

__initcall(cpucache_init);

/*
 * Interface to system's page allocator. No need to hold the cache-lock.
 *
 * If we requested dmaable memory, we will get it. Even if we
 * did not request dmaable memory, we might get it, but that
 * would be relatively rare and ignorable.
 */
static void *kmem_getpages(kmem_cache_t *cachep, unsigned int __nocast flags, int nodeid)
{
	struct page *page;
	void *addr;
	int i;

	flags |= cachep->gfpflags;
	if (likely(nodeid == -1)) {
		page = alloc_pages(flags, cachep->gfporder);
	} else {
		page = alloc_pages_node(nodeid, flags, cachep->gfporder);
	}
	if (!page)
		return NULL;
	addr = page_address(page);

	i = (1 << cachep->gfporder);
	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
		atomic_add(i, &slab_reclaim_pages);
	add_page_state(nr_slab, i);
	while (i--) {
		SetPageSlab(page);
		page++;
	}
	return addr;
}

/*
 * Interface to system's page release.
 */
static void kmem_freepages(kmem_cache_t *cachep, void *addr)
{
	unsigned long i = (1<<cachep->gfporder);
	struct page *page = virt_to_page(addr);
	const unsigned long nr_freed = i;

	while (i--) {
		if (!TestClearPageSlab(page))
			BUG();
		page++;
	}
	sub_page_state(nr_slab, nr_freed);
	if (current->reclaim_state)
		current->reclaim_state->reclaimed_slab += nr_freed;
	free_pages((unsigned long)addr, cachep->gfporder);
	if (cachep->flags & SLAB_RECLAIM_ACCOUNT) 
		atomic_sub(1<<cachep->gfporder, &slab_reclaim_pages);
}

static void kmem_rcu_free(struct rcu_head *head)
{
	struct slab_rcu *slab_rcu = (struct slab_rcu *) head;
	kmem_cache_t *cachep = slab_rcu->cachep;

	kmem_freepages(cachep, slab_rcu->addr);
	if (OFF_SLAB(cachep))
		kmem_cache_free(cachep->slabp_cache, slab_rcu);
}

#if DEBUG

#ifdef CONFIG_DEBUG_PAGEALLOC
static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr,
				unsigned long caller)
{
	int size = obj_reallen(cachep);

	addr = (unsigned long *)&((char*)addr)[obj_dbghead(cachep)];

	if (size < 5*sizeof(unsigned long))
		return;

	*addr++=0x12345678;
	*addr++=caller;
	*addr++=smp_processor_id();
	size -= 3*sizeof(unsigned long);
	{
		unsigned long *sptr = &caller;
		unsigned long svalue;

		while (!kstack_end(sptr)) {
			svalue = *sptr++;
			if (kernel_text_address(svalue)) {
				*addr++=svalue;
				size -= sizeof(unsigned long);
				if (size <= sizeof(unsigned long))
					break;
			}
		}

	}
	*addr++=0x87654321;
}
#endif

static void poison_obj(kmem_cache_t *cachep, void *addr, unsigned char val)
{
	int size = obj_reallen(cachep);
	addr = &((char*)addr)[obj_dbghead(cachep)];

	memset(addr, val, size);
	*(unsigned char *)(addr+size-1) = POISON_END;
}

static void dump_line(char *data, int offset, int limit)
{
	int i;
	printk(KERN_ERR "%03x:", offset);
	for (i=0;i<limit;i++) {
		printk(" %02x", (unsigned char)data[offset+i]);
	}
	printk("\n");
}
#endif

#if DEBUG

static void print_objinfo(kmem_cache_t *cachep, void *objp, int lines)
{
	int i, size;
	char *realobj;

	if (cachep->flags & SLAB_RED_ZONE) {
		printk(KERN_ERR "Redzone: 0x%lx/0x%lx.\n",
			*dbg_redzone1(cachep, objp),
			*dbg_redzone2(cachep, objp));
	}

	if (cachep->flags & SLAB_STORE_USER) {
		printk(KERN_ERR "Last user: [<%p>]",
				*dbg_userword(cachep, objp));
		print_symbol("(%s)",
				(unsigned long)*dbg_userword(cachep, objp));
		printk("\n");
	}
	realobj = (char*)objp+obj_dbghead(cachep);
	size = obj_reallen(cachep);
	for (i=0; i<size && lines;i+=16, lines--) {
		int limit;
		limit = 16;
		if (i+limit > size)
			limit = size-i;
		dump_line(realobj, i, limit);
	}
}

static void check_poison_obj(kmem_cache_t *cachep, void *objp)
{
	char *realobj;
	int size, i;
	int lines = 0;

	realobj = (char*)objp+obj_dbghead(cachep);
	size = obj_reallen(cachep);

	for (i=0;i<size;i++) {
		char exp = POISON_FREE;
		if (i == size-1)
			exp = POISON_END;
		if (realobj[i] != exp) {
			int limit;
			/* Mismatch ! */
			/* Print header */
			if (lines == 0) {
				printk(KERN_ERR "Slab corruption: start=%p, len=%d\n",
						realobj, size);
				print_objinfo(cachep, objp, 0);
			}
			/* Hexdump the affected line */
			i = (i/16)*16;
			limit = 16;
			if (i+limit > size)
				limit = size-i;
			dump_line(realobj, i, limit);
			i += 16;
			lines++;
			/* Limit to 5 lines */
			if (lines > 5)
				break;
		}
	}
	if (lines != 0) {
		/* Print some data about the neighboring objects, if they
		 * exist:
		 */
		struct slab *slabp = GET_PAGE_SLAB(virt_to_page(objp));
		int objnr;

		objnr = (objp-slabp->s_mem)/cachep->objsize;
		if (objnr) {
			objp = slabp->s_mem+(objnr-1)*cachep->objsize;
			realobj = (char*)objp+obj_dbghead(cachep);
			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
						realobj, size);
			print_objinfo(cachep, objp, 2);
		}
		if (objnr+1 < cachep->num) {
			objp = slabp->s_mem+(objnr+1)*cachep->objsize;
			realobj = (char*)objp+obj_dbghead(cachep);
			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
						realobj, size);
			print_objinfo(cachep, objp, 2);
		}
	}
}
#endif

/* Destroy all the objs in a slab, and release the mem back to the system.
 * Before calling the slab must have been unlinked from the cache.
 * The cache-lock is not held/needed.
 */
static void slab_destroy (kmem_cache_t *cachep, struct slab *slabp)
{
	void *addr = slabp->s_mem - slabp->colouroff;

#if DEBUG
	int i;
	for (i = 0; i < cachep->num; i++) {
		void *objp = slabp->s_mem + cachep->objsize * i;

		if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
			if ((cachep->objsize%PAGE_SIZE)==0 && OFF_SLAB(cachep))
				kernel_map_pages(virt_to_page(objp), cachep->objsize/PAGE_SIZE,1);
			else
				check_poison_obj(cachep, objp);
#else
			check_poison_obj(cachep, objp);
#endif
		}
		if (cachep->flags & SLAB_RED_ZONE) {
			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "start of a freed object "
							"was overwritten");
			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "end of a freed object "
							"was overwritten");
		}
		if (cachep->dtor && !(cachep->flags & SLAB_POISON))
			(cachep->dtor)(objp+obj_dbghead(cachep), cachep, 0);
	}
#else
	if (cachep->dtor) {
		int i;
		for (i = 0; i < cachep->num; i++) {
			void* objp = slabp->s_mem+cachep->objsize*i;
			(cachep->dtor)(objp, cachep, 0);
		}
	}
#endif

	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
		struct slab_rcu *slab_rcu;

		slab_rcu = (struct slab_rcu *) slabp;
		slab_rcu->cachep = cachep;
		slab_rcu->addr = addr;
		call_rcu(&slab_rcu->head, kmem_rcu_free);
	} else {
		kmem_freepages(cachep, addr);
		if (OFF_SLAB(cachep))
			kmem_cache_free(cachep->slabp_cache, slabp);
	}
}

1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
/* For setting up all the kmem_list3s for cache whose objsize is same
   as size of kmem_list3. */
static inline void set_up_list3s(kmem_cache_t *cachep, int index)
{
	int node;

	for_each_online_node(node) {
		cachep->nodelists[node] = &initkmem_list3[index+node];
		cachep->nodelists[node]->next_reap = jiffies +
			REAPTIMEOUT_LIST3 +
			((unsigned long)cachep)%REAPTIMEOUT_LIST3;
	}
}

Linus Torvalds's avatar
Linus Torvalds committed
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
/**
 * kmem_cache_create - Create a cache.
 * @name: A string which is used in /proc/slabinfo to identify this cache.
 * @size: The size of objects to be created in this cache.
 * @align: The required alignment for the objects.
 * @flags: SLAB flags
 * @ctor: A constructor for the objects.
 * @dtor: A destructor for the objects.
 *
 * Returns a ptr to the cache on success, NULL on failure.
 * Cannot be called within a int, but can be interrupted.
 * The @ctor is run when new pages are allocated by the cache
 * and the @dtor is run before the pages are handed back.
 *
 * @name must be valid until the cache is destroyed. This implies that
 * the module calling this has to destroy the cache before getting 
 * unloaded.
 * 
 * The flags are
 *
 * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
 * to catch references to uninitialised memory.
 *
 * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
 * for buffer overruns.
 *
 * %SLAB_NO_REAP - Don't automatically reap this cache when we're under
 * memory pressure.
 *
 * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
 * cacheline.  This can be beneficial if you're counting cycles as closely
 * as davem.
 */
kmem_cache_t *
kmem_cache_create (const char *name, size_t size, size_t align,
	unsigned long flags, void (*ctor)(void*, kmem_cache_t *, unsigned long),
	void (*dtor)(void*, kmem_cache_t *, unsigned long))
{
	size_t left_over, slab_size, ralign;
	kmem_cache_t *cachep = NULL;

	/*
	 * Sanity checks... these are all serious usage bugs.
	 */
	if ((!name) ||
		in_interrupt() ||
		(size < BYTES_PER_WORD) ||
		(size > (1<<MAX_OBJ_ORDER)*PAGE_SIZE) ||
		(dtor && !ctor)) {
			printk(KERN_ERR "%s: Early error in slab %s\n",
					__FUNCTION__, name);
			BUG();
		}

#if DEBUG
	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
	if ((flags & SLAB_DEBUG_INITIAL) && !ctor) {
		/* No constructor, but inital state check requested */
		printk(KERN_ERR "%s: No con, but init state check "
				"requested - %s\n", __FUNCTION__, name);
		flags &= ~SLAB_DEBUG_INITIAL;
	}

#if FORCED_DEBUG
	/*
	 * Enable redzoning and last user accounting, except for caches with
	 * large objects, if the increased size would increase the object size
	 * above the next power of two: caches with object sizes just above a
	 * power of two have a significant amount of internal fragmentation.
	 */
	if ((size < 4096 || fls(size-1) == fls(size-1+3*BYTES_PER_WORD)))
		flags |= SLAB_RED_ZONE|SLAB_STORE_USER;
	if (!(flags & SLAB_DESTROY_BY_RCU))
		flags |= SLAB_POISON;
#endif
	if (flags & SLAB_DESTROY_BY_RCU)
		BUG_ON(flags & SLAB_POISON);
#endif
	if (flags & SLAB_DESTROY_BY_RCU)
		BUG_ON(dtor);

	/*
	 * Always checks flags, a caller might be expecting debug
	 * support which isn't available.
	 */
	if (flags & ~CREATE_MASK)
		BUG();

	/* Check that size is in terms of words.  This is needed to avoid
	 * unaligned accesses for some archs when redzoning is used, and makes
	 * sure any on-slab bufctl's are also correctly aligned.
	 */
	if (size & (BYTES_PER_WORD-1)) {
		size += (BYTES_PER_WORD-1);
		size &= ~(BYTES_PER_WORD-1);
	}

	/* calculate out the final buffer alignment: */
	/* 1) arch recommendation: can be overridden for debug */
	if (flags & SLAB_HWCACHE_ALIGN) {
		/* Default alignment: as specified by the arch code.
		 * Except if an object is really small, then squeeze multiple
		 * objects into one cacheline.
		 */
		ralign = cache_line_size();
		while (size <= ralign/2)
			ralign /= 2;
	} else {
		ralign = BYTES_PER_WORD;
	}
	/* 2) arch mandated alignment: disables debug if necessary */
	if (ralign < ARCH_SLAB_MINALIGN) {
		ralign = ARCH_SLAB_MINALIGN;
		if (ralign > BYTES_PER_WORD)
			flags &= ~(SLAB_RED_ZONE|SLAB_STORE_USER);
	}
	/* 3) caller mandated alignment: disables debug if necessary */
	if (ralign < align) {
		ralign = align;
		if (ralign > BYTES_PER_WORD)
			flags &= ~(SLAB_RED_ZONE|SLAB_STORE_USER);
	}
	/* 4) Store it. Note that the debug code below can reduce
	 *    the alignment to BYTES_PER_WORD.
	 */
	align = ralign;

	/* Get cache's description obj. */
	cachep = (kmem_cache_t *) kmem_cache_alloc(&cache_cache, SLAB_KERNEL);
	if (!cachep)
		goto opps;
	memset(cachep, 0, sizeof(kmem_cache_t));

#if DEBUG
	cachep->reallen = size;

	if (flags & SLAB_RED_ZONE) {
		/* redzoning only works with word aligned caches */
		align = BYTES_PER_WORD;

		/* add space for red zone words */
		cachep->dbghead += BYTES_PER_WORD;
		size += 2*BYTES_PER_WORD;
	}
	if (flags & SLAB_STORE_USER) {
		/* user store requires word alignment and
		 * one word storage behind the end of the real
		 * object.
		 */
		align = BYTES_PER_WORD;
		size += BYTES_PER_WORD;
	}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
1620
	if (size >= malloc_sizes[INDEX_L3+1].cs_size && cachep->reallen > cache_line_size() && size < PAGE_SIZE) {
Linus Torvalds's avatar
Linus Torvalds committed
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
		cachep->dbghead += PAGE_SIZE - size;
		size = PAGE_SIZE;
	}
#endif
#endif

	/* Determine if the slab management is 'on' or 'off' slab. */
	if (size >= (PAGE_SIZE>>3))
		/*
		 * Size is large, assume best to place the slab management obj
		 * off-slab (should allow better packing of objs).
		 */
		flags |= CFLGS_OFF_SLAB;

	size = ALIGN(size, align);

	if ((flags & SLAB_RECLAIM_ACCOUNT) && size <= PAGE_SIZE) {
		/*
		 * A VFS-reclaimable slab tends to have most allocations
		 * as GFP_NOFS and we really don't want to have to be allocating
		 * higher-order pages when we are unable to shrink dcache.
		 */
		cachep->gfporder = 0;
		cache_estimate(cachep->gfporder, size, align, flags,
					&left_over, &cachep->num);
	} else {
		/*
		 * Calculate size (in pages) of slabs, and the num of objs per
		 * slab.  This could be made much more intelligent.  For now,
		 * try to avoid using high page-orders for slabs.  When the
		 * gfp() funcs are more friendly towards high-order requests,
		 * this should be changed.
		 */
		do {
			unsigned int break_flag = 0;
cal_wastage:
			cache_estimate(cachep->gfporder, size, align, flags,
						&left_over, &cachep->num);
			if (break_flag)
				break;
			if (cachep->gfporder >= MAX_GFP_ORDER)
				break;
			if (!cachep->num)
				goto next;
			if (flags & CFLGS_OFF_SLAB &&
					cachep->num > offslab_limit) {
				/* This num of objs will cause problems. */
				cachep->gfporder--;
				break_flag++;
				goto cal_wastage;
			}

			/*
			 * Large num of objs is good, but v. large slabs are
			 * currently bad for the gfp()s.
			 */
			if (cachep->gfporder >= slab_break_gfp_order)
				break;

			if ((left_over*8) <= (PAGE_SIZE<<cachep->gfporder))
				break;	/* Acceptable internal fragmentation. */
next:
			cachep->gfporder++;
		} while (1);
	}

	if (!cachep->num) {
		printk("kmem_cache_create: couldn't create cache %s.\n", name);
		kmem_cache_free(&cache_cache, cachep);
		cachep = NULL;
		goto opps;
	}
	slab_size = ALIGN(cachep->num*sizeof(kmem_bufctl_t)
				+ sizeof(struct slab), align);

	/*
	 * If the slab has been placed off-slab, and we have enough space then
	 * move it on-slab. This is at the expense of any extra colouring.
	 */
	if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
		flags &= ~CFLGS_OFF_SLAB;
		left_over -= slab_size;
	}

	if (flags & CFLGS_OFF_SLAB) {
		/* really off slab. No need for manual alignment */
		slab_size = cachep->num*sizeof(kmem_bufctl_t)+sizeof(struct slab);
	}

	cachep->colour_off = cache_line_size();
	/* Offset must be a multiple of the alignment. */
	if (cachep->colour_off < align)
		cachep->colour_off = align;
	cachep->colour = left_over/cachep->colour_off;
	cachep->slab_size = slab_size;
	cachep->flags = flags;
	cachep->gfpflags = 0;
	if (flags & SLAB_CACHE_DMA)
		cachep->gfpflags |= GFP_DMA;
	spin_lock_init(&cachep->spinlock);
	cachep->objsize = size;

	if (flags & CFLGS_OFF_SLAB)
1724
		cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
Linus Torvalds's avatar
Linus Torvalds committed
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
	cachep->ctor = ctor;
	cachep->dtor = dtor;
	cachep->name = name;

	/* Don't let CPUs to come and go */
	lock_cpu_hotplug();

	if (g_cpucache_up == FULL) {
		enable_cpucache(cachep);
	} else {
		if (g_cpucache_up == NONE) {
			/* Note: the first kmem_cache_create must create
			 * the cache that's used by kmalloc(24), otherwise
			 * the creation of further caches will BUG().
			 */
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
			cachep->array[smp_processor_id()] =
				&initarray_generic.cache;

			/* If the cache that's used by
			 * kmalloc(sizeof(kmem_list3)) is the first cache,
			 * then we need to set up all its list3s, otherwise
			 * the creation of further caches will BUG().
			 */
			set_up_list3s(cachep, SIZE_AC);
			if (INDEX_AC == INDEX_L3)
				g_cpucache_up = PARTIAL_L3;
			else
				g_cpucache_up = PARTIAL_AC;
Linus Torvalds's avatar
Linus Torvalds committed
1753
		} else {
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
			cachep->array[smp_processor_id()] =
				kmalloc(sizeof(struct arraycache_init),
						GFP_KERNEL);

			if (g_cpucache_up == PARTIAL_AC) {
				set_up_list3s(cachep, SIZE_L3);
				g_cpucache_up = PARTIAL_L3;
			} else {
				int node;
				for_each_online_node(node) {

					cachep->nodelists[node] =
						kmalloc_node(sizeof(struct kmem_list3),
								GFP_KERNEL, node);
					BUG_ON(!cachep->nodelists[node]);
					kmem_list3_init(cachep->nodelists[node]);
				}
			}
Linus Torvalds's avatar
Linus Torvalds committed
1772
		}
1773
1774
1775
1776
		cachep->nodelists[numa_node_id()]->next_reap =
			jiffies + REAPTIMEOUT_LIST3 +
			((unsigned long)cachep)%REAPTIMEOUT_LIST3;

Linus Torvalds's avatar
Linus Torvalds committed
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
		BUG_ON(!ac_data(cachep));
		ac_data(cachep)->avail = 0;
		ac_data(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
		ac_data(cachep)->batchcount = 1;
		ac_data(cachep)->touched = 0;
		cachep->batchcount = 1;
		cachep->limit = BOOT_CPUCACHE_ENTRIES;
	} 

	/* Need the semaphore to access the chain. */
	down(&cache_chain_sem);
	{
		struct list_head *p;
		mm_segment_t old_fs;

		old_fs = get_fs();
		set_fs(KERNEL_DS);
		list_for_each(p, &cache_chain) {
			kmem_cache_t *pc = list_entry(p, kmem_cache_t, next);
			char tmp;
			/* This happens when the module gets unloaded and doesn't
			   destroy its slab cache and noone else reuses the vmalloc
			   area of the module. Print a warning. */
			if (__get_user(tmp,pc->name)) { 
				printk("SLAB: cache with size %d has lost its name\n", 
					pc->objsize); 
				continue; 
			} 	
			if (!strcmp(pc->name,name)) { 
				printk("kmem_cache_create: duplicate cache %s\n",name); 
				up(&cache_chain_sem); 
				unlock_cpu_hotplug();
				BUG(); 
			}	
		}
		set_fs(old_fs);
	}

	/* cache setup completed, link it into the list */
	list_add(&cachep->next, &cache_chain);
	up(&cache_chain_sem);
	unlock_cpu_hotplug();
opps:
	if (!cachep && (flags & SLAB_PANIC))
		panic("kmem_cache_create(): failed to create slab `%s'\n",
			name);
	return cachep;
}
EXPORT_SYMBOL(kmem_cache_create);

#if DEBUG
static void check_irq_off(void)
{
	BUG_ON(!irqs_disabled());
}

static void check_irq_on(void)
{
	BUG_ON(irqs_disabled());
}

static void check_spinlock_acquired(kmem_cache_t *cachep)
{
#ifdef CONFIG_SMP
	check_irq_off();
1842
	assert_spin_locked(&cachep->nodelists[numa_node_id()]->list_lock);
Linus Torvalds's avatar
Linus Torvalds committed
1843
1844
#endif
}
1845
1846
1847
1848
1849
1850
1851
1852
1853

static inline void check_spinlock_acquired_node(kmem_cache_t *cachep, int node)
{
#ifdef CONFIG_SMP
	check_irq_off();
	assert_spin_locked(&cachep->nodelists[node]->list_lock);
#endif
}

Linus Torvalds's avatar
Linus Torvalds committed
1854
1855
1856
1857
#else
#define check_irq_off()	do { } while(0)
#define check_irq_on()	do { } while(0)
#define check_spinlock_acquired(x) do { } while(0)
1858
#define check_spinlock_acquired_node(x, y) do { } while(0)
Linus Torvalds's avatar
Linus Torvalds committed
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
#endif

/*
 * Waits for all CPUs to execute func().
 */
static void smp_call_function_all_cpus(void (*func) (void *arg), void *arg)
{
	check_irq_on();
	preempt_disable();

	local_irq_disable();
	func(arg);
	local_irq_enable();

	if (smp_call_function(func, arg, 1, 1))
		BUG();

	preempt_enable();
}

static void drain_array_locked(kmem_cache_t* cachep,
1880
				struct array_cache *ac, int force, int node);
Linus Torvalds's avatar
Linus Torvalds committed
1881
1882
1883
1884
1885

static void do_drain(void *arg)
{
	kmem_cache_t *cachep = (kmem_cache_t*)arg;
	struct array_cache *ac;
1886
	int node = numa_node_id();
Linus Torvalds's avatar
Linus Torvalds committed
1887
1888
1889

	check_irq_off();
	ac = ac_data(cachep);
1890
1891
1892
	spin_lock(&cachep->nodelists[node]->list_lock);
	free_block(cachep, ac->entry, ac->avail, node);
	spin_unlock(&cachep->nodelists[node]->list_lock);
Linus Torvalds's avatar
Linus Torvalds committed
1893
1894
1895
1896
1897
	ac->avail = 0;
}

static void drain_cpu_caches(kmem_cache_t *cachep)
{
1898
1899
1900
	struct kmem_list3 *l3;
	int node;

Linus Torvalds's avatar
Linus Torvalds committed
1901
1902
1903
	smp_call_function_all_cpus(do_drain, cachep);
	check_irq_on();
	spin_lock_irq(&cachep->spinlock);
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
	for_each_online_node(node)  {
		l3 = cachep->nodelists[node];
		if (l3) {
			spin_lock(&l3->list_lock);
			drain_array_locked(cachep, l3->shared, 1, node);
			spin_unlock(&l3->list_lock);
			if (l3->alien)
				drain_alien_cache(cachep, l3);
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
1914
1915
1916
	spin_unlock_irq(&cachep->spinlock);
}

1917
static int __node_shrink(kmem_cache_t *cachep, int node)
Linus Torvalds's avatar
Linus Torvalds committed
1918
1919
{
	struct slab *slabp;
1920
	struct kmem_list3 *l3 = cachep->nodelists[node];
Linus Torvalds's avatar
Linus Torvalds committed
1921
1922
	int ret;

1923
	for (;;) {
Linus Torvalds's avatar
Linus Torvalds committed
1924
1925
		struct list_head *p;

1926
1927
		p = l3->slabs_free.prev;
		if (p == &l3->slabs_free)
Linus Torvalds's avatar
Linus Torvalds committed
1928
1929
			break;

1930
		slabp = list_entry(l3->slabs_free.prev, struct slab, list);
Linus Torvalds's avatar
Linus Torvalds committed
1931
1932
1933
1934
1935
1936
#if DEBUG
		if (slabp->inuse)
			BUG();
#endif
		list_del(&slabp->list);

1937
1938
		l3->free_objects -= cachep->num;
		spin_unlock_irq(&l3->list_lock);
Linus Torvalds's avatar
Linus Torvalds committed
1939
		slab_destroy(cachep, slabp);
1940
		spin_lock_irq(&l3->list_lock);
Linus Torvalds's avatar
Linus Torvalds committed
1941
	}
1942
1943
	ret = !list_empty(&l3->slabs_full) ||
		!list_empty(&l3->slabs_partial);
Linus Torvalds's avatar
Linus Torvalds committed
1944
1945
1946
	return ret;
}

1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
static int __cache_shrink(kmem_cache_t *cachep)
{
	int ret = 0, i = 0;
	struct kmem_list3 *l3;

	drain_cpu_caches(cachep);

	check_irq_on();
	for_each_online_node(i) {
		l3 = cachep->nodelists[i];
		if (l3) {
			spin_lock_irq(&l3->list_lock);
			ret += __node_shrink(cachep, i);
			spin_unlock_irq(&l3->list_lock);
		}
	}
	return (ret ? 1 : 0);
}

Linus Torvalds's avatar
Linus Torvalds committed
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
/**
 * kmem_cache_shrink - Shrink a cache.
 * @cachep: The cache to shrink.
 *
 * Releases as many slabs as possible for a cache.
 * To help debugging, a zero exit status indicates all slabs were released.
 */
int kmem_cache_shrink(kmem_cache_t *cachep)
{
	if (!cachep || in_interrupt())
		BUG();

	return __cache_shrink(cachep);
}
EXPORT_SYMBOL(kmem_cache_shrink);

/**
 * kmem_cache_destroy - delete a cache
 * @cachep: the cache to destroy
 *
 * Remove a kmem_cache_t object from the slab cache.
 * Returns 0 on success.
 *
 * It is expected this function will be called by a module when it is
 * unloaded.  This will remove the cache completely, and avoid a duplicate
 * cache being allocated each time a module is loaded and unloaded, if the
 * module doesn't have persistent in-kernel storage across loads and unloads.
 *
 * The cache must be empty before calling this function.
 *
 * The caller must guarantee that noone will allocate memory from the cache
 * during the kmem_cache_destroy().
 */
int kmem_cache_destroy(kmem_cache_t * cachep)
{
	int i;
2002
	struct kmem_list3 *l3;
Linus Torvalds's avatar
Linus Torvalds committed
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027

	if (!cachep || in_interrupt())
		BUG();

	/* Don't let CPUs to come and go */
	lock_cpu_hotplug();

	/* Find the cache in the chain of caches. */
	down(&cache_chain_sem);
	/*
	 * the chain is never empty, cache_cache is never destroyed
	 */
	list_del(&cachep->next);
	up(&cache_chain_sem);

	if (__cache_shrink(cachep)) {
		slab_error(cachep, "Can't free all objects");
		down(&cache_chain_sem);
		list_add(&cachep->next,&cache_chain);
		up(&cache_chain_sem);
		unlock_cpu_hotplug();
		return 1;
	}

	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
2028
		synchronize_rcu();
Linus Torvalds's avatar
Linus Torvalds committed
2029

2030
	for_each_online_cpu(i)
Linus Torvalds's avatar
Linus Torvalds committed
2031
2032
2033
		kfree(cachep->array[i]);

	/* NUMA: free the list3 structures */
2034
2035
2036
2037
2038
2039
2040
	for_each_online_node(i) {
		if ((l3 = cachep->nodelists[i])) {
			kfree(l3->shared);
			free_alien_cache(l3->alien);
			kfree(l3);
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
2041
2042
2043
2044
2045
2046
2047
2048
2049
	kmem_cache_free(&cache_cache, cachep);

	unlock_cpu_hotplug();

	return 0;
}
EXPORT_SYMBOL(kmem_cache_destroy);

/* Get the memory for a slab management obj. */
2050
2051
static struct slab* alloc_slabmgmt(kmem_cache_t *cachep, void *objp,
			int colour_off, unsigned int __nocast local_flags)
Linus Torvalds's avatar
Linus Torvalds committed
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
{
	struct slab *slabp;
	
	if (OFF_SLAB(cachep)) {
		/* Slab management obj is off-slab. */
		slabp = kmem_cache_alloc(cachep->slabp_cache, local_flags);
		if (!slabp)
			return NULL;
	} else {
		slabp = objp+colour_off;
		colour_off += cachep->slab_size;
	}
	slabp->inuse = 0;
	slabp->colouroff = colour_off;
	slabp->s_mem = objp+colour_off;

	return slabp;
}

static inline kmem_bufctl_t *slab_bufctl(struct slab *slabp)
{
	return (kmem_bufctl_t *)(slabp+1);
}

static void cache_init_objs(kmem_cache_t *cachep,
			struct slab *slabp, unsigned long ctor_flags)
{
	int i;

	for (i = 0; i < cachep->num; i++) {
2082
		void *objp = slabp->s_mem+cachep->objsize*i;
Linus Torvalds's avatar
Linus Torvalds committed
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
#if DEBUG
		/* need to poison the objs? */
		if (cachep->flags & SLAB_POISON)
			poison_obj(cachep, objp, POISON_FREE);
		if (cachep->flags & SLAB_STORE_USER)
			*dbg_userword(cachep, objp) = NULL;

		if (cachep->flags & SLAB_RED_ZONE) {
			*dbg_redzone1(cachep, objp) = RED_INACTIVE;
			*dbg_redzone2(cachep, objp) = RED_INACTIVE;
		}
		/*
		 * Constructors are not allowed to allocate memory from
		 * the same cache which they are a constructor for.
		 * Otherwise, deadlock. They must also be threaded.
		 */
		if (cachep->ctor && !(cachep->flags & SLAB_POISON))
			cachep->ctor(objp+obj_dbghead(cachep), cachep, ctor_flags);

		if (cachep->flags & SLAB_RED_ZONE) {
			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "constructor overwrote the"
							" end of an object");
			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "constructor overwrote the"
							" start of an object");
		}
		if ((cachep->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep) && cachep->flags & SLAB_POISON)
	       		kernel_map_pages(virt_to_page(objp), cachep->objsize/PAGE_SIZE, 0);
#else
		if (cachep->ctor)
			cachep->ctor(objp, cachep, ctor_flags);
#endif
		slab_bufctl(slabp)[i] = i+1;
	}
	slab_bufctl(slabp)[i-1] = BUFCTL_END;
	slabp->free = 0;
}

static void kmem_flagcheck(kmem_cache_t *cachep, unsigned int flags)
{
	if (flags & SLAB_DMA) {
		if (!(cachep->gfpflags & GFP_DMA))
			BUG();
	} else {
		if (cachep->gfpflags & GFP_DMA)
			BUG();
	}
}

static void set_slab_attr(kmem_cache_t *cachep, struct slab *slabp, void *objp)
{
	int i;
	struct page *page;

	/* Nasty!!!!!! I hope this is OK. */
	i = 1 << cachep->gfporder;
	page = virt_to_page(objp);
	do {
		SET_PAGE_CACHE(page, cachep);
		SET_PAGE_SLAB(page, slabp);
		page++;
	} while (--i);
}

/*
 * Grow (by 1) the number of slabs within a cache.  This is called by
 * kmem_cache_alloc() when there are no active objs left in a cache.
 */
static int cache_grow(kmem_cache_t *cachep, unsigned int __nocast flags, int nodeid)
{
	struct slab	*slabp;
	void		*objp;
	size_t		 offset;
	unsigned int	 local_flags;
	unsigned long	 ctor_flags;
2159
	struct kmem_list3 *l3;
Linus Torvalds's avatar
Linus Torvalds committed
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190

	/* Be lazy and only check for valid flags here,
 	 * keeping it out of the critical path in kmem_cache_alloc().
	 */
	if (flags & ~(SLAB_DMA|SLAB_LEVEL_MASK|SLAB_NO_GROW))
		BUG();
	if (flags & SLAB_NO_GROW)
		return 0;

	ctor_flags = SLAB_CTOR_CONSTRUCTOR;
	local_flags = (flags & SLAB_LEVEL_MASK);
	if (!(local_flags & __GFP_WAIT))
		/*
		 * Not allowed to sleep.  Need to tell a constructor about
		 * this - it might need to know...
		 */
		ctor_flags |= SLAB_CTOR_ATOMIC;

	/* About to mess with non-constant members - lock. */
	check_irq_off();
	spin_lock(&cachep->spinlock);

	/* Get colour for the slab, and cal the next value. */
	offset = cachep->colour_next;
	cachep->colour_next++;
	if (cachep->colour_next >= cachep->colour)
		cachep->colour_next = 0;
	offset *= cachep->colour_off;

	spin_unlock(&cachep->spinlock);

2191
	check_irq_off();
Linus Torvalds's avatar
Linus Torvalds committed
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
	if (local_flags & __GFP_WAIT)
		local_irq_enable();

	/*
	 * The test for missing atomic flag is performed here, rather than
	 * the more obvious place, simply to reduce the critical path length
	 * in kmem_cache_alloc(). If a caller is seriously mis-behaving they
	 * will eventually be caught here (where it matters).
	 */
	kmem_flagcheck(cachep, flags);

2203
2204
2205
	/* Get mem for the objs.
	 * Attempt to allocate a physical page from 'nodeid',
	 */
Linus Torvalds's avatar
Linus Torvalds committed
2206
2207
2208
2209
2210
2211
2212
	if (!(objp = kmem_getpages(cachep, flags, nodeid)))
		goto failed;

	/* Get slab management. */
	if (!(slabp = alloc_slabmgmt(cachep, objp, offset, local_flags)))
		goto opps1;

2213
	slabp->nodeid = nodeid;
Linus Torvalds's avatar
Linus Torvalds committed
2214
2215
2216
2217
2218
2219
2220
	set_slab_attr(cachep, slabp, objp);

	cache_init_objs(cachep, slabp, ctor_flags);

	if (local_flags & __GFP_WAIT)
		local_irq_disable();
	check_irq_off();
2221
2222
	l3 = cachep->nodelists[nodeid];
	spin_lock(&l3->list_lock);
Linus Torvalds's avatar
Linus Torvalds committed
2223
2224

	/* Make slab active. */
2225
	list_add_tail(&slabp->list, &(l3->slabs_free));
Linus Torvalds's avatar
Linus Torvalds committed
2226
	STATS_INC_GROWN(cachep);
2227
2228
	l3->free_objects += cachep->num;
	spin_unlock(&l3->list_lock);
Linus Torvalds's avatar
Linus Torvalds committed
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
	return 1;
opps1:
	kmem_freepages(cachep, objp);
failed:
	if (local_flags & __GFP_WAIT)
		local_irq_disable();
	return 0;
}

#if DEBUG

/*
 * Perform extra freeing checks:
 * - detect bad pointers.
 * - POISON/RED_ZONE checking
 * - destructor calls, for caches with POISON+dtor
 */
static void kfree_debugcheck(const void *objp)